Optical satellite sensors, previously Landsat TM/ETM/OLI and now Sentinel-2 MSI, are the primary data sources for detection of clearing and regrowth in woodlands in Queensland. In this context, the Statewide Landcover and Tree Survey (SLATS) definition of woodlands is used, e.g. assemblages of woody plants, including stands of native vegetation, regrowth following clearing, plantations of native and exotic species, and woody weeds. Satellites using active imaging systems such as Synthetic Aperture Radar from the European Space Agency’s Sentinel-1 and its future BIOMASS mission, as well as the upcoming NISAR mission from NASA and India’s national space agency, have great potential to improve detection. These active sensors complement optical imagery as they: provide vegetation structural information, provide sub-canopy information, can collect imagery during day and night as well as in adverse weather conditions, and possess the ability to penetrate through clouds, smoke, and tree canopies. One of the major advantages to using imaging radar is the ability to detect structural information below the canopy, a feature inherent only to active sensors. This additional information paired with deep learning algorithms has the potential to improve the detection of woodland clearing and regrowth.

The Injune Landscape Collaborative Project will be used to test and develop clearing and regrowth methodologies. SLATS data, along with optical and radar imagery (i.e. Sentinel-2, Planet and Sentinel-1, ALOS PALSAR) will be the primary data used for development and validation. The outputs from this research contribute to vegetation management and environmental policies, as well as other initiatives including the Great Barrier Reef 2050 Quality program, the Land Restoration Fund, and bushfire management.

Early detection of wildfires is vital to reduce fire caused deaths and property loss, and to prevent disastrous impact on wildlife and the environment, as well as to minimize the economic loss of the government on firefighting. Traditional approaches to wildfire detection often have delays, for example, fire observation towers take time to install and run but they only cover a small area; others may tend to be uneconomical, such as spotter aircrafts which are expensive to run but only operable for a short time.

In recent years, more satellite data on earth surface observation become available and this opens the door for new methods to be developed, which are expected to be prompt in time when fires are still small. However, the current satellite image-based detection methods are still ineffective for early fire detection due to low spatial or temporal resolution of the sensors. That says, wildfires usually cannot be detected directly by the satellites until they have burnt for a relatively long time and to a relatively large scale.

Instead of direct fire detection, smoke detection is expected to an alternative method since smoke disperses very fast into the air and can be visibly detected by the satellites quicker than fire. However, there remains many challenges. First, smoke has similar characteristics with cloud, dust, haze, which are difficult to be visually distinguished most of the time. Due to this, the false positive rate of smoke detection remains high for most developed models. Second, smoke does not have fixed shapes, which usually change very fast especially when there are winds. This will dramatically increase the complexity of the smoke detection models. Furthermore, the characteristics of smoke are closely associated with the fuels and are subject to the local environmental conditions, which makes the detection models hard to be applied to a different area without further adjustment. The differences between the sensor specifications also raise challenges for model reapplication and integration.

This project aims to develop practical machine learning technologies which can address the above challenges for smoke detection based on satellite imagery. The technologies are expected to become a new way to address the fire detection problems in vast remote areas. The application of the technologies is hoped to reduce the cost of running remote fire towers, to mitigate the risks on people working at the towers, and to shorten the decision time between the start of the fire and proper reactions taken.

In this project we propose the development of a pilot to demonstrate the use of an Internet-of-Things (IoT) low cost satellite telecommunications solution as an end-to-end cost-effective means to transmit and aggregate, in near real time, automatically collected information from ground water bores in rural and regional areas, with a focus on environmental water monitoring.

To this end, the project will test the technical feasibility, reliability and cost-effectiveness of deploying an end-to-end IoT satcoms solution in a remote and harsh environment – including evaluating, procuring and deploying sensor technologies to measure water levels, pressure, salinity, temperature and flow in groundwater stations/bores and assessing the feasibility of these to operate autonomously; in addition the project will define and develop a prototype to provide a “universal” connectivity module for ground water markets. This approach will be compared to current scenarios where information is collected manually and sparsely in time.

Australia urgently requires verified, high quality, real time information on wildfire location and intensity.

This project proposes a satellite system of systems encompassing geostationary, polar orbiting and aerial based sensors for real time fire landscape attribution. The project will design and deliver a data and platform ecosystem to allow autonomous real time information on fire to be detected, processed and delivered to end users.

We present this project as two elements: 1) design and implementation of a data and platform ecosystem that will enable fire surveillance in real time from geostationary, polar-orbiting and aerial platformed sensors. This system of systems approach will allow for best available information to always be provided. 2) derivation of autonomous AI algorithms for the real time surveillance of fires and its attribution (e.g. burn severity, FRP etc.).

Satellite sensors in the ecosystem of systems will include JAXA’s Himawari-8, MODIS, VIIRS, Sentinel-2, DLR’s Firebird constellation, as well as in situ and drone- and high-altitude-platform based observations for calibration, validation and accuracy assessment.

This project is a partnership between SmartSat and CSIRO to develop ground-to-space 24/7 water quality monitoring technology for Australia’s waterways, reservoirs and coastal environments.

This Phase-0 project, 12 months in duration, addresses in-situ sensor technology readiness and a space-based concepts of operations through end user consultation (in coordination with Know the Market to Grow the Market project), requirements analysis, market analysis, data analytics processing with existing data sets, and a preliminary satellite mission design, for the development of a detailed business case and investment options analysis.

Water quality monitoring is an essential input to effective management of a key national resource that is distributed across the continent requiring new approaches to address the current limited capability. The SmartSat/CSIRO Aquawatch program will address remote sensing, and in-situ capabilities, with this proposal focusing on the former and the TRL levels of in-situ sensing technologies.

This project will provide options to coordinate across the current state-based approach and has the potential to position Australia as a global leader in water quality monitoring and management.

The space-based component of AquaWatch will be a world-first, custom water quality monitoring-focused satellite earth observation mission/constellation with a global footprint.

Learn more about CSIRO research missions.

The spectral and radiometric resolution in existing satellite data is insufficient for monitoring fuel conditions in Australia’s eucalypt-dominant bushland. The OzFuel (Australian Fuel Monitoring from Space) satellite mission will make use of sovereign technologies to deliver fuel hazard data, with the goal of improving Australia’s pre-fire monitoring, prediction, preparation, response and resilience.

Led by ANU, the 12-month project will deliver OzFuel Phase A with partners UNSW Canberra, Skykraft, Spiral Blue and LatConnect 60. The project involves end-to-end mission design at the ANCDF, verification of fuel biochemical properties to be sensed from space, and market analysis on the commercial potential of shortwave infrared data in parallel industry sectors.

The project will accelerate development of critical sovereign Earth observation space technologies including advanced sensors, edge processing and small satellite capabilities.